🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)
-
Updated
Apr 9, 2024 - Python
#
self-correction
Here are 17 public repositories matching this topic...
Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.
decoding self-improvement knowledge-distillation data-augmentation reasoning self-consistency preference-learning hallucination self-correction attention-head large-language-models chain-of-thought large-language-model internal-consistency self-feedback self-refine self-correct
-
Updated
Dec 7, 2024 - Jupyter Notebook
List of papers on Self-Correction of LLMs.
-
Updated
Dec 28, 2024
[ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
-
Updated
Mar 23, 2025 - Python
Scalable long read self-correction and assembly polishing with multiple sequence alignment
assembly ngs consensus correction long self msa reads contigs long-reads multiple-sequence-alignment polishing self-correction
-
Updated
Feb 6, 2024 - C++
[ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"
planning tree-search text-to-sql self-correction mathematical-reasoning large-language-models language-agent
-
Updated
Feb 23, 2024 - Python
A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and post-inference stages.
reinforcement-learning post-training self-correction reward-learning large-language-models llm llms reward-models reward-model reward-modeling guided-decoding test-time-scaling
-
Updated
Jun 13, 2025
[ICLR 2025 SSI-FM] Self-Taught Self-Correction for Small Language Models
-
Updated
May 10, 2025 - Jupyter Notebook
SCoRe: Training Language Models to Self-Correct via Reinforcement Learning
-
Updated
Jan 24, 2025 - Python
[ICLR 2025] Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate
-
Updated
Apr 22, 2025 - Python
Enhancing LLMs with LoRA
training reinforcement-learning data-generation lora quantization fine-tune reasoning fine-tuning distillation finetuning accuracy-analysis self-correction self-distillation quantization-aware-training chain-of-thought supervised-finetuning qlora chain-of-thought-reasoning finetuning-llms fine-tuning-llm
-
Updated
Sep 23, 2024
Official Implementation of "ProgCo: Program Helps Self-Correction of Large Language Models" (Accpeted at ACL2025 Main)
-
Updated
Jun 6, 2025 - Python
A recursive alignment framework for cognitive coherence, belief tracking, and contradiction repair.
alignment containment ai-safety cognitive-systems self-correction systems-architecture recursive-modeling belief-tracking identity-modeling pseudonymous-research internal-alignment
-
Updated
Apr 3, 2025
A Python-based Agentic RAG system that uses local LLMs (Ollama) for intelligent documentation crawling, summarization, and vector embeddings (Supabase). Features a self-correcting agentic loop that dynamically refines answers through tool usage and validation, providing a robust, local solution for accurate information retrieval and generation.
python crawler machine-learning natural-language-processing ai rag self-correction vector-database agent-framework supabase llm ollama agentic-ai
-
Updated
Jun 16, 2025 - Python
A recursive alignment framework for cognitive coherence, belief tracking, and contradiction repair.
alignment containment ai-safety cognitive-systems self-correction systems-architecture recursive-modeling belief-tracking identity-modeling pseudonymous-research internal-alignment
-
Updated
Jun 27, 2025
Ground-Truth-Guided Evaluation (GTGE) framework using a multi-agent Crew AI system to improve the self-correction capabilities of Large Language Models (LLMs).
-
Updated
Apr 18, 2025 - Python
HomebrewAgenticAI is a Python project that creates a simplified Retrieval Augmented Generation system, featuring a web crawler and a local Large Language Model for effective data handling. With its self-correcting agentic loop, this tool enhances the quality of generated answers, making it a practical solution for information retrieval. 🐙💻
python crawler machine-learning ai rag self-correction vector-database agent-framework supabase llm ollama agentic-ai
-
Updated
Jun 27, 2025 - Python
Improve this page
Add a description, image, and links to the self-correction topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the self-correction topic, visit your repo's landing page and select "manage topics."